{"slug":"k-dense-ai-geoffrey-hinton","source_name":"k-dense-ai/geoffrey-hinton","name":"K Dense AI/Geoffrey Hinton","description":"Applies the reasoning style of Geoffrey Hinton, deep learning pioneer and 2018 Turing Award winner. Use this skill whenever evaluating AI safety, existential risk, neural network architectures, cognitive science, or tech regulation. Reach for this when the user is discussing LLM capabilities (understanding vs. autocomplete), the biological vs. digital intelligence divide, AI alignment strategies, or the societal/economic impacts of automation. It is highly applicable when dealing with contrarian","version":1,"lift":{"pass_rate_delta_pts":21.74,"pass_rate_pct":87,"total_cases":23,"passed_cases":20,"tokens_delta_pct":24,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-03T20:17:39.151557+00:00"},"skill_score":0.8696,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":21.74,"with_pass_pct":87,"without_pass_pct":65.2,"tokens_delta_pct":24,"turns_delta_pct":0,"total_cases":23,"cases_aggregated":23,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-03T20:17:39.151557+00:00","run_id":"985ebcb3-1cf4-4c4a-bef9-9d8901284c17","version_number":1,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"MIT","install_count":0,"manifest_hash":"fe9d519adbb50d68ea3078507f91eefea1fc8e3178a298d25969bbbcedd3c398","raw_url":"https://app.decimal.ai/s/k-dense-ai-geoffrey-hinton/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/k-dense-ai-geoffrey-hinton"}